© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8835
    Prev
    Next
    INDEX
    Explanations

    mentions and opinions about political and legal matters as well as people involved in them.

    oai_token-act-pair · gemini-2.0-flash

    Cause and effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.61
    +#+#
    -0.59
    principalTable
    -0.58
    RectangleBorder
    -0.56
     незавершена
    -0.55
     OkHttpClient
    -0.55
     الاطلاع
    -0.49
     simplesmente
    -0.48
    partly
    -0.48
    Vezi
    -0.47
    POSITIVE LOGITS
    WAVE
    0.64
     Ent
    0.60
    displayquote
    0.59
     Resp
    0.59
     because
    0.56
    PhysRevLett
    0.54
    Ent
    0.54
     entrain
    0.53
     WAVE
    0.52
     Wave
    0.52
    Activations Density 6.946%

    No Known Activations